Rich speech-enabled applications are driving a new paradigm in customer relationships, helping to deliver significant bottom
line results and increased customer satisfaction over traditional touch-tone driven IVR applications.
To further accelerate the evolution of speech-enabled applications, Avaya offers Dialog Designer Elements, a free suite of
pre-packaged re-usable speech dialog modules for Avaya Orchestration Designer (previously known as Dialog Designer). Dialog
Designer Elements simplify the creation of speech applications, allowing you to get the most out of self-service solutions
using Avaya Experience Portal (previously known as Voice Portal) or Interactive Response.
Dialog Designer Elements jump start your speech-enabled applications by offering:
- Key functional elements often found in speech-enabled applications, including zip code, phone number and
credit card recognition modules.
- Built-in logic to support barge-in, timeouts, error handling, and re-prompting and retry thresholds based on
speech recognition confidence scoring.
- Support for both speech recognition and touch-tone inputs, making it easy to migrate existing applications without
rewriting the entire application.
- Professional quality recorded English language voice prompts and built-in Text-to-Speech (TTS) capabilities for
- Use of built-in grammars to preserve vendor independence and application development flexibility.
Dialog Designer Elements include the following modules:
- Alpha-numeric input
- Confirmation (Yes/No)
- Credit Card Information collection, including card type, expiration date and security code
- Date, including support for both speech and touchtone input methods
- Individual Digits ("zero" through "nine"), which can easily be used to add speech navigation to existing
touchtone based IVR applications without significant application redesign
- Numbers ("fifteen", "three hundred twenty seven", etc.)
- Phone Number
- Time, including "a.m." and "p.m." indicators
- ZIP Code collection
Use of Dialog Designer Elements can potentially save developers hundreds of hours in development and test time.
Furthermore, Dialog Designer Elements can be easily adapted using Avaya Dialog Designer, and re-used across
multiple application projects, shortening overall development cycles while lowering costs.
Features: Dialog Designer Elements are built to have industry-standard features and parameters including:
- Thresholds Timeouts
- Retry prompting using alternative prompts, based on confidence scoring
- Support for both Speech Recognition & Touch-tone input
- Barge-In support
- Transfer to Agent (using touchtone digit Zero)
Speech Recognition: Dialog Designer Elements are designed to be vendor-neutral as it pertains to
speech recognition, and have been tested using both Nuance and IBM speech recognition engines.
All prompting and caller input is designed around a directed dialog (DD) paradigm in which the caller is directed
to speak one datum per prompt.
The initial set of Dialog Designer Elements as released have been localized to support English-speaking callers via
pre-recorded professional voice quality prompts and U.S. English speech recognition grammars and Text-to-Speech
(TTS) capabilities. Developers can easily modify the Dialog Design Elements and replace the pre-recorded prompts in
order to support additional languages for both speech recognition and TTS.
Grammars: Dialog Designer Elements use built-in grammars exclusively, allowing for maximum flexibility
in the choice of a speech recognition engine for deployment with Avaya Voice Portal or Avaya Interactive Response.
Developers can modify and tailor the Dialog Designer Elements with customized grammars supported by their desired
recognition engine. As an example of this work, the Credit Card Dialog Designer Element has been also built to take
advantage of the Nuance credit card grammar in those cases where a developer is using a speech platform configured with
Confidence Scores: Speech recognition applications use confidence scoring to evaluate the quality of
the caller input. The confidence score is an indicator of how closely the caller's utterance matches the phrases
specified in the grammar.
- No Input from caller: Used when the application doesn't receive any discernible response from the caller, No Input results in a general re-prompt message, "I'm not hearing you."
- Low Confidence Recognition of caller recognition: Indicates that the application received input, but can't be sure what the caller really said. A typical message in this case is "Say again please."
- Medium Confidence Recognition: Indicates that the application received input, but needs to confirm the caller's response with a message such as "<speaking back response>" Is this correct?"
- High Confidence Recognition: Used when the application receives non-ambiguous input which was scored above the high confidence score threshold. In this case, the application accepts the response and continues.
Dialog Designer Elements were developed in conjunction with Avaya DevConnect partners GM Voices (www.gmvoices.com)
and Gold Systems (www.goldsys.com)